Performance Analysis of LSTMs for Daily Individual EV Charging Behavior Prediction

In this paper, we evaluate and analyze the performance of long short-term memory networks (LSTMs) for individual electric vehicle (EV) charging behavior prediction over the next day. The charging behavior consists of the charging duration level within a certain upper and lower range, the time slots...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Ahmed S. Khwaja, Bala Venkatesh, Alagan Anpalagan
Formato: article
Lenguaje:EN
Publicado: IEEE 2021
Materias:
Acceso en línea:https://doaj.org/article/2c1b90ffa9264d209a2757be23306aea
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:2c1b90ffa9264d209a2757be23306aea
record_format dspace
spelling oai:doaj.org-article:2c1b90ffa9264d209a2757be23306aea2021-11-25T00:00:55ZPerformance Analysis of LSTMs for Daily Individual EV Charging Behavior Prediction2169-353610.1109/ACCESS.2021.3128491https://doaj.org/article/2c1b90ffa9264d209a2757be23306aea2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9615185/https://doaj.org/toc/2169-3536In this paper, we evaluate and analyze the performance of long short-term memory networks (LSTMs) for individual electric vehicle (EV) charging behavior prediction over the next day. The charging behavior consists of the charging duration level within a certain upper and lower range, the time slots in which charging will take place, the number of times charging will take place in each time slot, and whether the next day will be a charging day or not. Unlike existing work, we evaluate the behavior prediction performance for increasing resolutions of charging duration levels and charging time slots, using varying lengths of training data. The performance of the proposed approach is validated using real EV charging data, and comparison with other machine learning methods shows its generally superior prediction accuracy for all resolutions. We show that the best performance is achieved when around 8–10 months of data are used as training data. It is also shown that although the performance of the LSTMs degrades with increasing resolution, the performance for charging time slot prediction is affected less compared to that for charging duration prediction. We further propose, analyze and evaluate a new technique that improves the charging duration prediction performance.Ahmed S. KhwajaBala VenkateshAlagan AnpalaganIEEEarticleElectric vehiclecharging predictiondeep learninglong short-term memory networksElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 154804-154814 (2021)
institution DOAJ
collection DOAJ
language EN
topic Electric vehicle
charging prediction
deep learning
long short-term memory networks
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
spellingShingle Electric vehicle
charging prediction
deep learning
long short-term memory networks
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
Ahmed S. Khwaja
Bala Venkatesh
Alagan Anpalagan
Performance Analysis of LSTMs for Daily Individual EV Charging Behavior Prediction
description In this paper, we evaluate and analyze the performance of long short-term memory networks (LSTMs) for individual electric vehicle (EV) charging behavior prediction over the next day. The charging behavior consists of the charging duration level within a certain upper and lower range, the time slots in which charging will take place, the number of times charging will take place in each time slot, and whether the next day will be a charging day or not. Unlike existing work, we evaluate the behavior prediction performance for increasing resolutions of charging duration levels and charging time slots, using varying lengths of training data. The performance of the proposed approach is validated using real EV charging data, and comparison with other machine learning methods shows its generally superior prediction accuracy for all resolutions. We show that the best performance is achieved when around 8–10 months of data are used as training data. It is also shown that although the performance of the LSTMs degrades with increasing resolution, the performance for charging time slot prediction is affected less compared to that for charging duration prediction. We further propose, analyze and evaluate a new technique that improves the charging duration prediction performance.
format article
author Ahmed S. Khwaja
Bala Venkatesh
Alagan Anpalagan
author_facet Ahmed S. Khwaja
Bala Venkatesh
Alagan Anpalagan
author_sort Ahmed S. Khwaja
title Performance Analysis of LSTMs for Daily Individual EV Charging Behavior Prediction
title_short Performance Analysis of LSTMs for Daily Individual EV Charging Behavior Prediction
title_full Performance Analysis of LSTMs for Daily Individual EV Charging Behavior Prediction
title_fullStr Performance Analysis of LSTMs for Daily Individual EV Charging Behavior Prediction
title_full_unstemmed Performance Analysis of LSTMs for Daily Individual EV Charging Behavior Prediction
title_sort performance analysis of lstms for daily individual ev charging behavior prediction
publisher IEEE
publishDate 2021
url https://doaj.org/article/2c1b90ffa9264d209a2757be23306aea
work_keys_str_mv AT ahmedskhwaja performanceanalysisoflstmsfordailyindividualevchargingbehaviorprediction
AT balavenkatesh performanceanalysisoflstmsfordailyindividualevchargingbehaviorprediction
AT alagananpalagan performanceanalysisoflstmsfordailyindividualevchargingbehaviorprediction
_version_ 1718414686232248320